Advertisement

A Study on Dictionary Learning Based Image Reconstruction Techniques for Big Medical Data

  • Shailendra TiwariEmail author
  • Kavkirat Kaur
  • K. V. Arya
Chapter

Abstract

Nowadays, Dictionary Learning (DL) based reconstruction techniques plays a significant role in the quality of CT image reconstruction. The basic principle behind all the reconstruction algorithm is to reconstruct acceptable images from the noisy and incomplete sparse datasets collected from the different projection views around the object (patient). Generally, the amount of data collected during the acquisition process suffers by large-scale matrix factorization problem. To analyze or solve this sparse representation of training images signals into a compressed form without amplifying the noise has proven to be a more difficult task. Dictionary Learning (DL) is an efficient algorithm to optimize and to present the desired output for accurate clinical diagnosis. The work presented in this work mainly focuses on the comprehensive study of both the basic and advanced aspects of DL reconstruction algorithms for analyzing the big medical data. Also, presents the extensive literature survey of existing state-of-the-art researches by knowledgeable authors that discuss the pros and cons with some conclusive remarks.

References

  1. 1.
    Aharon, Michal and Elad, Michael and Bruckstein, rmk-SVD: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on signal processing (2006).  https://doi.org/10.1109/TSP.2006.881199.zbMATHCrossRefGoogle Scholar
  2. 2.
    Andersen, Anders H and Kak, Avinash C, Simultaneous algebraic reconstruction technique (SART): a superior implementation of the ART algorithm. Ultrasonic imaging (1984). https://doi.org/10.1016/0161-7346(84)90008-7.CrossRefGoogle Scholar
  3. 3.
    Brono, A and Osshausen, BA, Emergence of simple-cell receptive field properties by learning a sparse code for natural image. Nature (1996). https://doi.org/10.1038/381607a0.CrossRefGoogle Scholar
  4. 4.
    Bruyant, Philippe P, Analytic and iterative reconstruction algorithms in SPECT. Journal of Nuclear Medicine (2002) 1;43(10):1343–58.Google Scholar
  5. 5.
    Bruyant, Philippe P, Analytic and iterative reconstruction algorithms in SPECT, Journal of Nuclear Medicine, Soc Nuclear Med (2002) https://doi.org/10.1016/j.patcog.2016.09.038.CrossRefGoogle Scholar
  6. 6.
    Chen, Scott Shaobing and Donoho, David L and Saunders, Michael A, Analytic and iterative reconstruction algorithms in SPECT. SIAM review (2001). https://doi.org/10.1137/S003614450037906X.MathSciNetzbMATHCrossRefGoogle Scholar
  7. 7.
    Chen, Scott Shaobing and Donoho, David L and Saunders, Michael A, Sparse representation and dictionary learning penalized image reconstruction for positron emission tomography. Physics in Medicine Biology, IOP Publishing (2015). https://doi.org/10.1088/0031-9155/60/2/807.CrossRefGoogle Scholar
  8. 8.
    Chen, Yang and Shi, Luyao and Feng, Qianjing and Yang, Jian and Shu, Huazhong and Luo, Limin and Coatrieux, Jean-Louis and Chen, Wufan, Artifact suppressed dictionary learning for low-dose CT image processing. IEEE transactions on medical imaging (2014).  https://doi.org/10.1109/TMI.2014.2336860.CrossRefGoogle Scholar
  9. 9.
    Chen, Yang and Yin, Xindao and Shi, Luyao and Shu, Huazhong and Luo, Limin and Coatrieux, Jean-Louis and Toumoulin, Christine, Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing. Physics in Medicine & Biology, IOP Publishing (2013). https://doi.org/10.1088/0031-9155/58/16/5803.CrossRefGoogle Scholar
  10. 10.
    Devaney, Anthony J, A filtered backpropagation algorithm for diffraction tomography. Ultrasonic imaging, Elsevier (1982). https://doi.org/10.1016/0161-7346(82)90017-7.CrossRefGoogle Scholar
  11. 11.
    Elad, Michael, From exact to approximate solutions. Sparse and Redundant Representations, Springer (2010).CrossRefGoogle Scholar
  12. 12.
    Elad, Michael and Aharon, Michal, Image denoising via sparse and redundant representations over learned dictionaries. IEEE Transactions on Image processing, Springer (2006).  https://doi.org/10.1109/TIP.2006.881969.MathSciNetCrossRefGoogle Scholar
  13. 13.
    Engan, Kjersti and Aase, Sven Ole and Husy, John Hkon, Multi-frame compression: Theory and design. Signal Processing, Elsevier (2000). https://doi.org/10.1016/S0165-1684(00)00072-4.zbMATHCrossRefGoogle Scholar
  14. 14.
    Etter, Vincent and Jovanovic, Ivana and Vetterli, Martin, Use of learned dictionaries in tomographic reconstruction. Wavelets and Sparsity XIV, International Society for Optics and Photonics, Elsevier (2011), vol. 8138, pp. 81381C.Google Scholar
  15. 15.
    Fang, Ruogu and Zhang, Shaoting and Chen, Tsuhan and Sanelli, Pina C, Robust low-dose CT perfusion deconvolution via tensor total-variation regularization. IEEE transactions on medical imaging (2015),  https://doi.org/10.1109/TMI.2015.2405015.CrossRefGoogle Scholar
  16. 16.
    Gilbert, Peter, Iterative methods for the three-dimensional reconstruction of an object from projections. Journal of theoretical biology, Elsevier (1972). https://doi.org/10.1016/0022-5193(72)90180-4.CrossRefGoogle Scholar
  17. 17.
    Gopi, Varun P and Palanisamy, P and Wahid, Khan A and Babyn, Paul and Cooper, David, Iterative computed tomography reconstruction from sparse-view data. Journal of Medical Imaging and Health Informatics, American Scientific Publishers (2016).  https://doi.org/10.1166/jmihi.2016.1579.CrossRefGoogle Scholar
  18. 18.
    Gordon, Richard and Bender, Robert and Herman, Gabor T, Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and X-ray photography. Journal of theoretical Biology, Elsevier (1970). https://doi.org/10.1016/0022-5193(70)90109-8.CrossRefGoogle Scholar
  19. 19.
    Green, Peter J, Bayesian reconstructions from emission tomography data using a modified EM algorithm. IEEE transactions on medical imaging, IEEE (1990). https://doi.org/10.1109/42.52985.CrossRefGoogle Scholar
  20. 20.
    Greffier, J and Macri, F and Larbi, A and Fernandez, A and Pereira, F and Mekkaoui, C and Beregi, J-P, Dose reduction with iterative reconstruction in multi-detector CT: what is the impact on deformation of circular structures in phantom study? Diagnostic and interventional imaging, Elsevier (2016). https://doi.org/10.1016/j.diii.2015.06.019.Google Scholar
  21. 21.
    Greffier, J and Macri, F and Larbi, A and Fernandez, A and Khasanova, E and Pereira, F and Mekkaoui, C and Beregi, JP, Dose reduction with iterative reconstruction: optimization of CT protocols in clinical practice. Diagnostic and interventional imaging, Elsevier (2015). https://doi.org/10.1016/j.diii.2015.02.007.Google Scholar
  22. 22.
    Hansen, Per Christian and Saxild-Hansen, Maria, AIR tools: a MATLAB package of algebraic iterative reconstruction methods. Journal of Computational and Applied Mathematics, Elsevier (2012). https://doi.org/10.1016/j.cam.2011.09.039.MathSciNetzbMATHCrossRefGoogle Scholar
  23. 23.
    He, Qian and Huang, Lihong, Penalized maximum likelihood algorithm for positron emission tomography by using anisotropic median-diffusion. Mathematical Problems in Engineering, Hindawi (2014). https://doi.org/10.1155/2014/491239.MathSciNetzbMATHGoogle Scholar
  24. 24.
    Hoyer, Patrik O, Non-negative matrix factorization with sparseness constraints. Journal of machine learning research, (2004), vol 5, Pages 1457–1469.Google Scholar
  25. 25.
    Huang, Yue and Paisley, John and Lin, Qin and Ding, Xinghao and Fu, Xueyang and Zhang, Xiao-Ping, Bayesian nonparametric dictionary learning for compressed sensing MRI. IEEE Transactions on Image Processing, IEEE (2014).  https://doi.org/10.1109/TIP.2014.2360122.MathSciNetzbMATHCrossRefGoogle Scholar
  26. 26.
    Kang, Eunhee and Min, Junhong and Ye, Jong Chul, A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. Medical physics, Wiley Online Library (2017). https://doi.org/10.1002/mp.12344.CrossRefGoogle Scholar
  27. 27.
    Kolehmainen, Ville and Lassas, Matti and Niinimäki, Kati and Siltanen, Samuli, Sparsity-promoting Bayesian inversion. Inverse Problems, IOP Publishing, vol 28, no. 2, pp. 025005 (2012).MathSciNetzbMATHCrossRefGoogle Scholar
  28. 28.
    Kreutz-Delgado, Kenneth and Murray, Joseph F and Rao, Bhaskar D and Engan, Kjersti and Lee, Te-Won and Sejnowski, Terrence J, Dictionary learning algorithms for sparse representation. Neural computation, MIT Press (2003). https://doi.org/10.1162/089976603762552951.zbMATHCrossRefGoogle Scholar
  29. 29.
    Lee, Daniel D and Seung, H Sebastian, Learning the parts of objects by non-negative matrix factorization. Nature, Nature Publishing Group (1999). https://doi.org/10.1038/44565.zbMATHCrossRefGoogle Scholar
  30. 30.
    Lee, Honglak and Battle, Alexis and Raina, Rajat and Ng, Andrew Y, Efficient sparse coding algorithms, Advances in neural information processing systems, Proceedings of the 2006 Conference, pp. 801–808 (2007).Google Scholar
  31. 31.
    Lee, Daniel D and Seung, H Sebastian, An efficient dictionary learning algorithm and its application to 3-D medical image denoising. Nature, IEEE Transactions on Biomedical Engineering (2012).  https://doi.org/10.1109/TBME.2011.2173935.CrossRefGoogle Scholar
  32. 32.
    Li, Si and Cao, Qing and Chen, Yang and Hu, Yining and Luo, Limin and Toumoulin, Christine, Dictionary learning based sinogram inpainting for CT sparse reconstruction, Optik-International Journal for Light and Electron Optics, Elsevier (2014). https://doi.org/10.1016/j.ijleo.2014.01.003.CrossRefGoogle Scholar
  33. 33.
    Liao, Hstau Y and Sapiro, Guillermo, Sparse representations for limited data tomography, 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro (2008).  https://doi.org/10.1109/ISBI.2008.4541261.
  34. 34.
    Liu, Baodong and Yu, Hengyong and Verbridge, Scott S and Sun, Lizhi and Wang, Ge, Dictionary-learning-based reconstruction method for electron tomography, Scanning, Wiley Online Library (2014).  https://doi.org/10.1002/sca.21121.
  35. 35.
    Lu, Xiaoqiang and Huang, Zihan and Yuan, Yuan, MR image super-resolution via manifold regularized sparse learning, Neurocomputing, Elsevier (2015). https://doi.org/10.1016/j.neucom.2015.03.065.CrossRefGoogle Scholar
  36. 36.
    Mairal, Julien and Bach, Francis and Ponce, Jean and Sapiro, Guillermo, Online learning for matrix factorization and sparse coding, Journal of Machine Learning Research, vol. 11, pp.19–60 (2010). arXiv:0908.0050.Google Scholar
  37. 37.
    Mairal, Julien and Bach, Francis and Ponce, Jean and Sapiro, Guillermo and Zisserman, Andrew, Discriminative learned dictionaries for local image analysis, Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on IEEE (2008).  https://doi.org/10.1109/CVPR.2008.4587652.
  38. 38.
    Mairal, Julien and Sapiro, Guillermo and Elad, Michael, Learning multiscale sparse representations for image and video restoration, Multiscale Modeling & Simulation SIAM (2008). https://doi.org/10.1137/070697653.MathSciNetzbMATHCrossRefGoogle Scholar
  39. 39.
    Mirone, Alessandro and Brun, Emmanuel and Coan, Paola, A dictionary learning approach with overlap for the low dose computed tomography reconstruction and its vectorial application to differential phase tomography, PloS one, Public Library of Science (2014).  https://doi.org/10.1371/journal.pone.0114325.CrossRefGoogle Scholar
  40. 40.
    Murphy, Kevin P and Crush, Lee and O Neill, Siobhan B and Foody, James and Breen, Micheál and Brady, Adrian and Kelly, Paul J and Power, Derek G and Sweeney, Paul and Bye, Jackie and others, Feasibility of low-dose CT with model-based iterative image reconstruction in follow-up of patients with testicular cancer, European journal of radiology open, Elsevier (2016). https://doi.org/10.1016/j.ejro.2016.01.002.CrossRefGoogle Scholar
  41. 41.
    Nagata, Koichi and Fujiwara, Masanori and Kanazawa, Hidenori and Mogi, Tomohiro and Iida, Nao and Mitsushima, Toru and Lefor, Alan T and Sugimoto, Hideharu, Evaluation of dose reduction and image quality in CT colonography: comparison of low-dose CT with iterative reconstruction and routine-dose CT with filtered back projection, European radiology, Springer (2015). https://doi.org/10.1007/s00330-014-3350-3.CrossRefGoogle Scholar
  42. 42.
    Oda, Seitaro and Utsunomiya, Daisuke and Funama, Yoshinori and Katahira, Kazuhiro and Honda, Keiichi and Tokuyasu, Shinichi and Vembar, Mani and Yuki, Hideaki and Noda, Katsuo and Oshima, Shuichi and others, A knowledge-based iterative model reconstruction algorithm: can super-low-dose cardiac CT be applicable in clinical settings? Academic radiology, Elsevier (2014). https://doi.org/10.1016/j.acra.2013.10.002.CrossRefGoogle Scholar
  43. 43.
    Pathak, Yadunath and Arya, KV and Tiwari, Shailendra, Low-dose CT image reconstruction using gain intervention-based dictionary learning, Modern Physics Letters B, World Scientific (2018). https://doi.org/10.1142/S0217984918501488.MathSciNetCrossRefGoogle Scholar
  44. 44.
    Perona, Pietro and Malik, Jitendra, Scale-space and edge detection using anisotropic diffusion, IEEE Transactions on pattern analysis and machine intelligence, IEEE (1990). https://doi.org/10.1109/34.56205.CrossRefGoogle Scholar
  45. 45.
    Qi, Jinyi and Leahy, Richard M, Iterative reconstruction techniques in emission computed tomography, Physics in Medicine & Biology, IOP Publishing (2006). https://doi.org/10.1088/0031-9155/51/15/R01.CrossRefGoogle Scholar
  46. 46.
    Ravishankar, Saiprasad and Bresler, Yoram, MR image reconstruction from highly undersampled k-space data by dictionary learning, IEEE transactions on medical imaging, IEEE (2011).  https://doi.org/10.1109/TMI.2010.2090538.CrossRefGoogle Scholar
  47. 47.
    Soltani, Sara and Andersen, Martin S and Hansen, Per Christian, Tomographic image reconstruction using training images, Journal of Computational and Applied Mathematics, Elsevier (2017). https://doi.org/10.1016/j.cam.2016.09.019.MathSciNetzbMATHCrossRefGoogle Scholar
  48. 48.
    Strohmer, Thomas and Vershynin, Roman, A randomized Kaczmarz algorithm with exponential convergence, Journal of Fourier Analysis and Applications, Springer, vol. 15, no. 2, pp. 262 (2009).Google Scholar
  49. 49.
    Takx, Richard AP and Schoepf, U Joseph and Moscariello, Antonio and Das, Marco and Rowe, Garrett and Schoenberg, Stefan O and Fink, Christian and Henzler, Thomas, Coronary CT angiography: comparison of a novel iterative reconstruction with filtered back projection for reconstruction of low-dose CT a initial experience, European journal of radiology, Elsevier (2013). https://doi.org/10.1016/j.ejrad.2012.10.021.CrossRefGoogle Scholar
  50. 50.
    Tian, Zhen and Jia, Xun and Yuan, Kehong and Pan, Tinsu and Jiang, Steve B, Low-dose CT reconstruction via edge-preserving total variation regularization, Physics in Medicine & Biology, IOP Publishing (2011). https://doi.org/10.1088/0031-9155/56/18/011.CrossRefGoogle Scholar
  51. 51.
    Tošić, Ivana and Jovanović, Ivana and Frossard, Pascal and Vetterli, Martin and Durić, Neb, Ultrasound tomography with learned dictionaries, Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on IEEE (2011).  https://doi.org/10.1109/ICASSP.2010.5495211.
  52. 52.
    Tropp, Joel A and Wright, Stephen J, Computational methods for sparse solution of linear inverse problems, Proceedings of the IEEE, IEEE (2010).  https://doi.org/10.1109/JPROC.2010.2044010.CrossRefGoogle Scholar
  53. 53.
    Wang, Rui and Schoepf, U Joseph and Wu, Runze and Reddy, Ryan P and Zhang, Chuanchen and Yu, Wei and Liu, Yi and Zhang, Zhaoqi, Image quality and radiation dose of low dose coronary CT angiography in obese patients: sinogram affirmed iterative reconstruction versus filtered back projection, European journal of radiology, Elsevier (2012). https://doi.org/10.1016/j.ejrad.2012.04.012.CrossRefGoogle Scholar
  54. 54.
    Wieczorek, Matthias and Frikel, Jürgen and Vogel, Jakob and Eggl, Elena and Kopp, Felix and Noël, Peter B and Pfeiffer, Franz and Demaret, Laurent and Lasser, Tobias, X-ray computed tomography using curvelet sparse regularization, Medical physics, Wiley Online Library (2015). https://doi.org/10.1118/1.4914368.CrossRefGoogle Scholar
  55. 55.
    Willemink, Martin J and Leiner, Tim and de Jong, Pim A and de Heer, Linda M and Nievelstein, Rutger AJ and Schilham, Arnold MR and Budde, Ricardo PJ, Iterative reconstruction techniques for computed tomography part 2: initial results in dose reduction and image quality, European radiology, Springer (2013). https://doi.org/10.1007/s00330-012-2764-z.CrossRefGoogle Scholar
  56. 56.
    Xu, Qiong and Yu, Hengyong and Mou, Xuanqin and Zhang, Lei and Hsieh, Jiang and Wang, Ge, Low-dose X-ray CT reconstruction via dictionary learning, IEEE Transactions on Medical Imaging, IEEE (2012).  https://doi.org/10.1109/TMI.2012.2195669.CrossRefGoogle Scholar
  57. 57.
    XYuki, Hideaki and Oda, Seitaro and Utsunomiya, Daisuke and Funama, Yoshinori and Kidoh, Masafumi and Namimoto, Tomohiro and Katahira, Kazuhiro and Honda, Keiichi and Tokuyasu, Shinichi and Yamashita, Yasuyuki, Clinical impact of model-based type iterative reconstruction with fast reconstruction time on image quality of low-dose screening chest CT, Acta Radiologica, SAGE Publications Sage UK: London, England (2016). https://doi.org/10.1177/0284185115575537.CrossRefGoogle Scholar
  58. 58.
    Zhang, Cheng and Zhang, Tao and Li, Ming and Peng, Chengtao and Liu, Zhaobang and Zheng, Jian, Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares, Biomedical engineering online, BioMed Central (2016). https://doi.org/10.1186/s12938-016-0193-y.
  59. 59.
    Donoho, David and Stodden, Victoria, When does non-negative matrix factorization give a correct decomposition into parts? Advances in neural information processing systems (2004). https://doi.org/10.1186/s12938-016-0193-y.
  60. 60.
    Zhang, Cheng and Zhang, Tao and Li, Ming and Peng, Chengtao and Liu, Zhaobang and Zheng, Jian, Statistical image reconstruction for low-dose CT using nonlocal means-based regularization. Part II: An adaptive approach, Computerized Medical Imaging and Graphics, Elsevier (2015). https://doi.org/10.1016/j.compmedimag.2015.02.008.CrossRefGoogle Scholar
  61. 61.
    Zhang, Hao and Ma, Jianhua and Wang, Jing and Liu, Yan and Lu, Hongbing and Liang, Zhengrong, Statistical image reconstruction for low-dose CT using nonlocal means-based regularization, Computerized Medical Imaging and Graphics, Elsevier (2014). https://doi.org/10.1016/j.compmedimag.2014.05.002.CrossRefGoogle Scholar
  62. 62.
    Bulla, Stefan and Blanke, Philipp and Hassepass, Frederike and Krauss, Tobias and Winterer, Jan Thorsten and Breunig, Christine and Langer, Mathias and Pache, Gregor, Reducing the radiation dose for low-dose CT of the paranasal sinuses using iterative reconstruction: feasibility and image quality, European journal of radiology, Elsevier (2012). https://doi.org/10.1016/j.ejrad.2011.05.002.CrossRefGoogle Scholar
  63. 63.
    Zhang, Junfeng and Hu, Yining and Yang, Jian and Chen, Yang and Coatrieux, Jean-Louis and Luo, Limin, Sparse-view X-ray CT reconstruction with Gamma regularization, Neurocomputing, Elsevier (2017). https://doi.org/10.1016/j.neucom.2016.12.019.CrossRefGoogle Scholar
  64. 64.
    Zhao, Bo and Ding, Huanjun and Lu, Yang and Wang, Ge and Zhao, Jun and Molloi, Sabee, Dual-dictionary learning-based iterative image reconstruction for spectral computed tomography application, Physics in Medicine & Biology, IOP Publishing (2012). https://doi.org/10.1088/0031-9155/57/24/8217.CrossRefGoogle Scholar
  65. 65.
    Zhou, Mingyuan and Chen, Haojun and Paisley, John and Ren, Lu and Li, Lingbo and Xing, Zhengming and Dunson, David and Sapiro, Guillermo and Carin, Lawrence, Nonparametric Bayesian dictionary learning for analysis of noisy and incomplete images, IEEE Transactions on Image Processing, IEEE (2012).  https://doi.org/10.1109/TIP.2011.2160072.MathSciNetzbMATHCrossRefGoogle Scholar
  66. 66.
    Zonoobi, Dornoosh and Roohi, Shahrooz F and Kassim, Ashraf A and Jaremko, Jacob L, Dependent nonparametric bayesian group dictionary learning for online reconstruction of dynamic mr images, Pattern Recognition, Elsevier (2017). https://doi.org/10.1016/j.patcog.2016.09.038.CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringThapar Institute of Engineering and TechnologyPatialaIndia
  2. 2.Computer Science & Engineering (CSE), Institute of Engineering & TechnologyLucknowIndia

Personalised recommendations